WilliamsA. x 2

bookMasked language modeling and the distributional hypothesis: Order word matters pre-training for little

A possible explanation for the impressive performance of masked language model (MLM) pre-training is...

PineauJ.WilliamsA.SinhaK.JiaR.HupkesD.

bookHi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models

… finetuned on several dialogue datasets that were designed to impart the model with a wi...

SmithE.M.WilliamsA.